Player profile
Fusion
An open-source, multi-node agent orchestrator where a planning agent turns a plain-language task into a PROMPT.md plan, then runs plan, review, execute, and review gates for each task in an isolated git worktree, controllable from desktop, web, mobile, or the fn CLI.
Profile
Where it fits
Fusion is an open-source, multi-node agent orchestrator that plans tasks into PROMPT.md specs and runs them through plan, review, execute, and review gates inside isolated git worktrees, controllable from desktop, web, mobile, or the fn CLI.
It belongs in Open Orchestrators because it coordinates many agents and tasks as shared board state across a synced mesh of peer nodes, with hierarchical missions, inter-agent messaging, and per-project model lanes for local and cloud providers.
Builder web analytics
Measure projects built with Fusion
Fusion ships tasks autonomously through worktree-isolated workflow gates. Agent Analytics gives the next agent real visitor and conversion data after a merged task reaches a user-facing surface.
Use Agent Analytics after Fusion tasks ship user-facing work so completed tasks and missions are judged by reported web and product outcomes, not only board status.
First loop to measure
- a task is planned, executed, and reviewed through Fusion's workflow gates in an isolated worktree
- the merged change ships to the website, docs, app, onboarding flow, or support surface
- the changed surface reports visits, sources, signup, activation, retention, or funnel movement to Agent Analytics
- a follow-up agent fetches the outcome report and turns it into the next task or mission
Copyable prompt
Use Agent Analytics for this project. If event reporting is missing, add the tracker and report events for this project surface, including Fusion-built page, traffic source, signup, activation event, retention change, or shipped task. Verify events are arriving. Then fetch the last 7 days and compare them with the prior 7 days. Tell me which Fusion-built page, traffic source, signup, activation event, retention change, or shipped task moved users toward value, where users dropped off, which sources mattered, and what my agent workflow should improve next.